© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 204822
    Prev
    Next
    INDEX
    Explanations

    transition words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    érieurs
    0.44
    inction
    0.39
     நிலையம்
    0.38
    collections
    0.38
    ␥
    0.38
     unsecured
    0.37
    ievements
    0.37
     creatively
    0.37
     রোড
    0.37
    гээ
    0.36
    POSITIVE LOGITS
     dots
    0.42
     Mint
    0.41
     Z
    0.39
     Hope
    0.38
     Jens
    0.38
     adapta
    0.38
     drž
    0.38
     Hugo
    0.37
     Metast
    0.37
     Than
    0.37
    Activations Density 0.001%

    No Known Activations